🏠 Home 🔬 Research 🩺 Battery Diagnostics 🤖 AI / ML 💻 Technology Platforms 📄 Publications 📚 Resources 📬 Contact
Collaborate With Us
Next-Generation Battery Intelligence Platform

EV Battery
Health &
Diagnostics

Advanced Lithium-ion Battery Degradation Research and
Intelligent Battery Health Monitoring Systems

Developing intelligent diagnostics, battery health monitoring systems, and predictive AI models to understand lithium-ion battery degradation and improve safety, reliability, and performance in electric vehicles.

🔬 Lithium-ion Battery Degradation 📊 SOC | SOH | RUL Monitoring 🤖 AI-Driven Battery Diagnostics
Explore Research → View Technology

Towards safer, longer-lasting, and intelligent EV battery systems.

SOH Status
94.7%
State of Health
RUL Forecast
847 cycles
Remaining Useful Life
Thermal Alert
Cell #7 monitoring
🔬
5+
Research Domains
⚗️
10+
Battery Aging Concepts
📊
SOC/SOH/RUL
Health Monitoring Focus
🤖
AI-First
Predictive Diagnostics
RESEARCH TEAM

About the Researchers

A cross-disciplinary team bridging materials science, electrochemistry, AI, and EV engineering to advance battery health intelligence.

Shilajit Das
Shilajit Das
RESEARCH SCHOLAR
Degradation of Lithium-ion Battery
MME, NITK Surathkal
Lead Researcher
Specialisation: Lithium-ion Battery Degradation Research — electrochemical degradation mechanisms, SEI layer formation, cathode aging, and capacity fade analysis.
📞 +91 82403 07388 ✉️ shilajit.me29@gmail.com 🎓 shilajitdas.207mt006@nitk.edu.in
Sudarshana Karkala
Sudarshana Karkala
EV.ENGINEER™
AI-Driven EV Predictive Maintenance
NITK Surathkal (Alumni), EVE&D, IIT M(CODE)
Co-Researcher Principal Architect
Focus Areas: EV Battery Fire Prevention Systems, AI-driven predictive maintenance, software-defined battery diagnostics, and intelligent EV safety platforms.
📞 +91 98455 61518 ✉️ sudarshana.karkala@gmail.com 🔗 linkedin.com/in/sudarshanakarkala
OUR PURPOSE

Research Vision

To advance the scientific understanding of lithium-ion battery degradation and build intelligent battery health monitoring systems that enable safer, longer-lasting, and more reliable EV energy systems — contributing to a cleaner, smarter, and more sustainable future of mobility.

⚗️
Degradation Science

Deep electrochemical investigation of degradation mechanisms at the molecular, particle, and cell levels — SEI growth, lithium plating, cathode structural changes.

🧠
Battery Intelligence

Building intelligent monitoring frameworks that accurately estimate SOC, SOH, and RUL in real time using data-driven and physical models.

🛡️
AI-Powered Safety

Detecting early thermal runaway precursors and safety-critical events using anomaly detection, risk scoring, and predictive AI systems.

CORE RESEARCH

Research & Development Areas

Five interconnected research pillars spanning electrochemistry, data science, AI, and systems engineering for advanced EV battery intelligence.

⚡
Lithium-ion Battery Degradation

Electrochemical degradation mechanisms, SEI layer formation, lithium plating, cathode aging, electrolyte decomposition, and capacity fade analysis across charge cycles and calendar aging.

SEI GrowthCapacity FadeLi Plating
📊
Battery Health Monitoring

State estimation including SOC, SOH, RUL, and DoD. Internal resistance tracking, battery diagnostics, real-time performance monitoring, and degradation trend analysis.

SOCSOHRULDoD
🛡️
Battery Safety Diagnostics

Thermal runaway precursor detection, anomaly identification, early warning systems, safety analytics, and fire prevention concepts for EV battery packs.

Thermal RunawayAnomaly Detection
🤖
AI-Driven Battery Analytics

Battery degradation prediction using machine learning models, health scoring algorithms, fault detection pipelines, and predictive maintenance systems for EV fleets.

ML ModelsHealth ScoringFault Detection
🔗
Intelligent Energy Management

Smart control and monitoring systems for EV battery packs, connected diagnostics platforms, and energy intelligence systems for optimized battery performance and longevity.

BMSConnected Diagnostics
🌐
Open Research Collaboration

Engaging with EV OEMs, battery manufacturers, academic institutions, and AI startups to accelerate battery health science and translate research into real-world applications.

Join Research
ARCHITECTURE

Battery Diagnostics Intelligence Pipeline

A structured end-to-end pipeline from raw battery signals to actionable diagnostics and predictive intelligence.

1
🔌 Sensors
Voltage, current, temperature, impedance, and battery pack telemetry collection.
2
📦 Data Acquisition
BMS logging, structured battery data collection and time-series storage.
3
⚙️ Pre-Processing
Noise filtering, signal conditioning, feature extraction, and normalization.
4
🤖 AI Analysis
ML models for degradation trend detection, anomaly identification, and behaviour analysis.
5
📊 Health Scoring
SOC, SOH, and RUL estimation with diagnostic indicators and risk scores.
6
🛡️ Predictive Maintenance
Battery safety alerts, degradation forecasting, and maintenance intelligence.
DEEP SCIENCE

Understanding Battery Degradation

A rigorous scientific examination of the mechanisms that drive lithium-ion battery aging — from the atomic scale to full-pack behaviour.

🧪
SEI Layer Growth
Solid Electrolyte Interphase formation consumes lithium inventory and increases internal resistance over cycling.
Electrochemical
❄️
Lithium Plating
Metallic lithium deposits on anode surface during fast charging or low-temperature operation, causing safety risks.
Safety Critical
🔩
Cathode Structural Degradation
Phase transitions, particle cracking, and structural disorder in cathode materials reduce energy capacity.
Material Science
⚗️
Electrolyte Decomposition
Electrolyte oxidation and reduction reactions produce gases and resistive byproducts inside the cell.
Chemistry
🗜️
Mechanical Stress in Electrodes
Volume changes during intercalation/deintercalation induce mechanical fatigue, cracking, and loss of contact.
Mechanical
📉
Capacity Fade
Cumulative loss of cyclable lithium and active material resulting in measurable reduction of cell energy throughput.
Performance
📈
Internal Resistance Growth
Rising ohmic and charge-transfer resistance due to interface degradation, limiting power delivery capability.
Impedance
📅
Calendar Aging
Time-dependent degradation occurring even when the battery is at rest, influenced by SOC level and temperature.
Time-Based
🔄
Cycle Aging
Charge–discharge cycling progressively degrades cell components through cumulative electrochemical stress.
Usage-Based
🌡️
Thermal Stress Effects
High temperature operation and gradients accelerate chemical reactions, SEI growth, and electrolyte decomposition.
Thermal
MONITORING FRAMEWORK

Battery Health Monitoring Concepts

Key state estimation and diagnostic indicators that define the health monitoring framework for intelligent battery systems.

SOC
State of Charge

Real-time estimation of remaining usable energy relative to full capacity. Foundation for accurate range prediction in EVs.

SOH
State of Health

Ratio of present maximum capacity to rated capacity. The primary degradation health indicator for battery lifecycle management.

RUL
Remaining Useful Life

Predicted number of remaining cycles until the battery reaches end-of-life threshold. Critical for predictive maintenance scheduling.

DoD
Depth of Discharge

Percentage of battery capacity used in a cycle. Higher DoD accelerates electrode stress and overall cell degradation rate.

CE
Coulombic Efficiency

Ratio of charge extracted to charge input per cycle. Deviations indicate parasitic reactions and active lithium loss events.

Ri
Internal Resistance Tracking

Monitoring ohmic and charge-transfer resistance growth as a functional degradation signature for battery health scoring.

T-Risk
Temperature-Based Risk Monitoring

Continuous temperature profiling to detect abnormal heat generation, hot spots, and early thermal runaway precursor signatures.

BAD
Battery Aging Diagnostics

Integrated diagnostic framework combining multiple state estimators for a comprehensive battery health picture over its lifecycle.

ARTIFICIAL INTELLIGENCE

AI-Driven Battery Intelligence

Applying machine learning, diagnostic analytics, and future digital twin approaches to understand battery degradation and predict health and safety risks.

📈
Battery Degradation Prediction

Data-driven models trained on electrochemical feature vectors to forecast SOH trajectory and capacity fade progression.

🔧
Predictive Maintenance Models

ML pipelines that estimate RUL and optimal maintenance windows to reduce unplanned failures in EV battery systems.

🔍
Battery Failure Pattern Recognition

Identifying recurring degradation signatures and failure modes from historical cycling data to anticipate future cell behavior.

🪞
Battery Digital Twin Concepts

Virtual representations of physical battery cells that evolve with real-world data for simulation, testing, and health tracking.

🚨
Anomaly Detection for Battery Safety

Unsupervised and supervised anomaly detection to identify out-of-norm behavior that may indicate safety-critical conditions.

🎯
Battery Risk Scoring Systems

Composite risk scores derived from multi-parameter health indicators to provide a single actionable battery safety index.

⭐ Featured Research Project

AI-Powered EV Battery
Fire Prevention System

An intelligent diagnostic platform that uses real-time battery telemetry, machine learning anomaly detection, and thermal risk modeling to identify early indicators of thermal runaway — preventing battery fires before they occur. Designed for integration with next-generation BMS architectures in EV passenger vehicles, two-wheelers, and commercial fleets.

Thermal Runaway Prevention Real-time Monitoring ML Anomaly Detection BMS Integration
Learn More →
🔥
PRODUCT VISION

Technology Platforms

Research-to-product platform concepts designed to bring battery intelligence to EV manufacturers, fleet operators, and battery pack makers.

📡
EV Battery Health Monitoring Platform

Real-time tracking of battery pack condition, health indicators, and diagnostic insights across the full vehicle fleet. Continuous SOC, SOH, and internal resistance monitoring with dashboard visualization.

Real-timeFleet ScaleDashboard
🔮
Battery Predictive Maintenance Platform

Using cycling data and AI models to forecast degradation trends, estimate RUL, and generate maintenance intelligence — reducing unplanned downtime and extending battery pack usable life.

RUL PredictionAI-DrivenMaintenance
🛡️
Battery Safety Analytics Platform

Identifying early risk indicators related to thermal instability, lithium plating risk, and safety-critical events. Designed for OEM integration and fleet safety management systems.

SafetyThermal RiskOEM Ready
⚡
Intelligent Energy Diagnostics Platform

Integration of software-driven diagnostics, energy intelligence, and battery management for advanced EV systems. Enables smart, connected, data-informed battery operation at scale.

Software-DefinedBMSEnergy Intelligence
REAL-WORLD IMPACT

Industry Applications

Research translated into practical value across the full EV ecosystem — from passenger vehicles to industrial energy storage.

🚗
Electric Passenger Vehicles

Health monitoring and predictive diagnostics for sedan, SUV, and hatchback EV battery packs. Improved range prediction through accurate SOC/SOH estimation.

→ Range accuracy & battery longevity
🛵
Electric Two-Wheelers

Lightweight battery diagnostics tailored for high-cycle-frequency two-wheeler use patterns. Relevant to Indian OEMs like Ola, Ather, TVS, and Bajaj.

→ Compact, high-frequency diagnostics
🚌
Commercial EV Fleets

Fleet-level battery health intelligence, predictive maintenance scheduling, and degradation analytics for buses, trucks, and delivery vehicles.

→ Fleet uptime & cost reduction
🏭
Battery Pack Manufacturers

End-of-line diagnostics, aging characterization, and quality intelligence tools for battery pack production and testing environments.

→ Quality control & yield improvement
🔋
Energy Storage Systems

Health monitoring and lifecycle management for stationary lithium-ion energy storage used in grid, solar, and commercial applications.

→ Stationary storage reliability
🤖
AI-Driven EV Safety Platforms

Software companies and AI startups building next-generation battery safety, telematics, and diagnostics products for the global EV market.

→ Safety-as-a-Service for EV
INDUSTRY VALUE

Why This Matters to EV Industry

⚡
Better Battery Reliability

Intelligent diagnostics reduce unexpected failures, enabling OEMs to deliver more reliable electric vehicles with stronger warranty programs and customer confidence.

⏳
Longer Usable Battery Life

Understanding degradation mechanisms enables smart charging strategies and usage optimization that extend pack life beyond standard warranty cycles.

🛡️
Improved Safety Monitoring

Early anomaly detection and thermal risk intelligence prevent battery fires, protecting drivers, property, and brand reputation for OEMs and fleet operators.

📉
Reduced Field Failures

Predictive diagnostics identify batteries approaching failure before field incidents occur — reducing costly recalls, warranty claims, and service interventions.

🔮
Stronger Battery Intelligence for Future EVs

Building the foundational AI and data systems required for autonomous battery management in next-generation EV architectures and solid-state batteries.

🔋
94.7%
Target SOH at 1000 cycles
3×
Faster diagnosis vs manual
Early
Thermal risk detection
AI
Driven RUL forecasting
↓
Field failure rate target

"Battery intelligence is no longer optional — it's the cornerstone of safe, reliable, and competitive electric vehicles."

RESEARCH OUTPUTS

Publications & Research Outputs

Ongoing research documentation, knowledge contributions, and future innovation directions in battery health and diagnostics.

Research Papers
📄
Lithium-ion Battery Degradation Studies

Electrochemical analysis and aging characterisation of Li-ion cells under varied cycling conditions. Work in progress — NITK Surathkal.

Patents
⚖️
Battery Diagnostics Innovation (Placeholder)

Patent concepts in battery safety diagnostics and health monitoring are being explored. Details to be disclosed upon filing.

Technical Reports
📋
Battery Aging & Health Monitoring Framework

Technical documentation of SOC, SOH, and RUL estimation methods applied to lithium-ion battery datasets.

Innovation Ideas
💡
AI-Driven Battery Fire Prevention

Conceptual design of an intelligent EV battery fire prevention system using real-time telemetry and ML-based anomaly detection.

Datasets
🗄️
Battery Cycling & Degradation Data

Structured datasets from battery cycling experiments for degradation modelling and health monitoring algorithm training.

Future Roadmap
🗺️
Battery Intelligence Research Roadmap

Planned research directions including digital twin development, edge BMS intelligence, and industry collaboration projects for 2025–2027.

EXPERTISE

Skills & Capabilities

A deep cross-disciplinary skill set spanning electrochemistry, artificial intelligence, and EV systems engineering.

⚗️
Battery Research Skills
Electrochemical Analysis
Battery Aging Studies
Degradation Modelling
Battery Diagnostics
Battery Safety Concepts
🤖
AI & Software Skills
Python
Machine Learning
Data Analytics
Simulation Models
Predictive Systems Design
🚗
EV Systems Skills
Battery Pack Diagnostics
Energy Management Systems
Battery Health Monitoring
Safety Engineering
Software-Driven Monitoring
Knowledge Asset

EV Battery Degradation Atlas

A visual scientific map tracing the complete degradation journey of a lithium-ion battery — from early-stage subtle changes to advanced aging and safety-critical conditions. Understanding each stage enables targeted intervention strategies.

Stage 01
Early-Stage Degradation
Minor SEI growth
Coulombic efficiency > 99.5%
Capacity loss < 5%
Electrolyte stable
No visible Li plating
SOH ≥ 95%
Stage 02
Mid-Life Battery Aging
SEI thickening observed
Capacity loss 5–20%
Resistance growth 10–30%
Cathode micro-cracking
SOH 80–95%
Performance decline visible
Stage 03
Advanced Degradation Signs
Significant capacity fade
Li plating risk elevated
Electrolyte decomposition products
Gas generation detected
SOH 70–80%
Power fade prominent
Stage 04
Thermal Instability / End-of-Life
Thermal runaway risk
Lithium dendrite formation
Severe resistance growth
Cell swelling / venting risk
SOH < 70%
Replacement recommended
OPEN COLLABORATION

Research Collaboration

Open to collaboration with EV OEMs, battery manufacturers, research laboratories, universities, and AI-driven mobility startups working on battery health, safety, and predictive diagnostics.

EV OEMs Battery Manufacturers Research Laboratories Universities & IITs AI Mobility Startups Battery Pack Makers Safety Tech Companies EV Fleet Operators
Collaborate With Us →
GET IN TOUCH

Contact Us

Reach out for research collaboration, industry partnerships, or to learn more about our battery health and diagnostics work.

Research & Collaboration Enquiries

Whether you're an OEM, research lab, battery startup, or R&D team — we welcome conversations about battery intelligence, diagnostics, and AI-driven EV safety systems.

Shilajit Das
Lead Researcher · NITK Surathkal, Metallurgical & Materials Engineering
📞+91 82403 07388
✉️shilajit.me29@gmail.com
🎓shilajitdas.207mt006@nitk.edu.in
Sudarshana Karkala
Co-Researcher · EV.ENGINEER™ · AI & EV Predictive Maintenance
📞+91 98455 61518
✉️sudarshana.karkala@gmail.com
🔗linkedin.com/in/sudarshanakarkala
Send a Message